distillery logo
distillery
★ 25
vs
ken logo
ken
★ 33

distillery vs ken

distillery: Distillery is a team knowledge base accessed through Claude Code skills. It captures, classifies, connects, and surfaces team knowledge using natural language commands. It stores knowledge as vector embeddings in DuckDB, running locally or as a hosted service.; ken: Ken is a pure Go port of semble, providing fast hybrid code search for agents with drop-in MCP compatibility. It offers a single static binary distribution, approximately 44x fewer tokens than grep+Read at recall@10, and supports indexing source code and documentation. The retrieval algorithm is a verbatim port of semble's hybrid BM25 + Model2Vec approach.

01

TL;DR

distillery logo
distilleryRAG / Knowledge Base · ★ 25

Capture and retrieve team knowledge during development

ken logo
kenRAG / Knowledge Base · ★ 33

Agent code search: quickly find relevant code chunks across large codebases

02

Side-by-Side Comparison

Field
distillery logodistillery
ken logoken
Category
RAG / Knowledge Base
RAG / Knowledge Base
Stars
★ 25
★ 33
License
NOASSERTION
MIT
Install Command
claude plugin marketplace add norrietaylor/distillery && claude plugin install distillery
go install github.com/townsendmerino/ken/cmd/ken@latest && go install github.com/townsendmerino/ken/cmd/ken-mcp@latest && ken download-model
Updated
3d ago
1d ago
Open Source
Yes
Yes
Tags
claude-code, duckdb, embeddings
agents, bm25, code-search
03

Features

distillery logodistillery
01/distill - Capture session knowledge with dedup detection
02/recall - Semantic search with provenance
03/pour - Multi-entry synthesis with citations
04/bookmark - Store URLs with auto-generated summaries
05/digest - Team activity summary from internal entries
ken logoken
01Pure Go, no cgo; single static binary with free cross-compilation
02Drop-in MCP-compatible with semble (same tool schemas and output format)
03Verbatim port of semble's hybrid BM25 + Model2Vec retrieval algorithm
04Measured ~44x fewer tokens than grep+Read at recall@10 on agent queries
05Fast cold start (~10–20ms for small indexes)
04

Use Cases

distillery logodistillery
↳Capture and retrieve team knowledge during development
↳Record meeting minutes with append updates
↳Track technical decisions and architectural context
ken logoken
↳Agent code search: quickly find relevant code chunks across large codebases
↳Embedded-corpus distribution: ship documentation as a single static binary with zero infrastructure
↳Database schema indexing: index live Postgres/SQLite/MySQL schemas for agent context
FAQ

FAQ

What is the difference between distillery and ken?
Both distillery and ken are in the RAG / Knowledge Base category. distillery has 25 stars, while ken has 33 stars.
Which is better, distillery or ken?
The best choice depends on your use case. Choose distillery if Capture and retrieve team knowledge during development, and ken if Agent code search: quickly find relevant code chunks across large codebases.
Is distillery free or open source?
Yes, distillery is open source on GitHub (NOASSERTION).
Is ken free or open source?
Yes, ken is open source on GitHub (MIT).
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
→

Related